Global search
Top results
MAP670U - Monte Carlo Methods: from MCMC to Data -based Generative Model (2022-2023)
A new paradigm of generative models has emerged in AI in the last decade. It aims at designing a generative model mimicking a distribution described by a data set. It has mainly two applications: data augmentation, i.e. to generate new data statistically coherent with those of the initial (training) data set; digital twin, i.e. to replace a costly physical simulation model with an easy-to-use one. This has huge applications in image generation, fashion pictures, chemical molecules... this is ...
MAP670U-2022
MAP670U - Monte Carlo Methods: from MCMC to Data -based Generative Model (2023-2024)
A new paradigm of generative models has emerged in AI in the last decade. It aims at designing a generative model mimicking a distribution described by a data set. It has mainly two applications: data augmentation, i.e. to generate new data statistically coherent with those of the initial (training) data set; digital twin, i.e. to replace a costly physical simulation model with an easy-to-use one. This has huge applications in image generation, fashion pictures, chemical molecules... this is ...
MAP670U-2023
MAP670U - Monte Carlo Methods: from MCMC to Data -based Generative Model (2022-2023)
A new paradigm of generative models has emerged in AI in the last decade. It aims at designing a generative model mimicking a distribution described by a data set. It has mainly two applications: data augmentation, i.e. to generate new data statistically coherent with those of the initial (training) data set; digital twin, i.e. to replace a costly physical simulation model with an easy-to-use one. This has huge applications in image generation, fashion pictures, chemical molecules... this is ...
MAP670U-2022
MAP670U - Monte Carlo Methods: from MCMC to Data -based Generative Model (2023-2024)
A new paradigm of generative models has emerged in AI in the last decade. It aims at designing a generative model mimicking a distribution described by a data set. It has mainly two applications: data augmentation, i.e. to generate new data statistically coherent with those of the initial (training) data set; digital twin, i.e. to replace a costly physical simulation model with an easy-to-use one. This has huge applications in image generation, fashion pictures, chemical molecules... this is ...
MAP670U-2023